Large language models might reason—if you know how to speak to them - TechTalks

He discovered that by adding the phrase “Let's think step by step” to the prompt, he could improve the performance of the model. He later found out that applying the same prompt to many other tasks triggered similar results.

This article is part of our coverage of the latest in AI research. Large language models (LLM), neural networks trained on huge corpora of text (or other types of data) have become a hot topic of di… [+11288 chars]

full article...